Merge pull request NVIDIA#355 from GrzegorzKarchNV/taco2-trt-table-update

update perf table for taco2 trt

Author: GrzegorzKarchNV

PyTorch/SpeechSynthesis/Tacotron2/trt/README.md

@@ -85,5 +85,5 @@ Our results were obtained by running the `./trt/run_latency_tests_trt.sh` script
 
 |Framework|Batch size|Input length|Precision|Avg latency (s)|Latency std (s)|Latency confidence interval 90% (s)|Latency confidence interval 95% (s)|Latency confidence interval 99% (s)|Throughput (samples/sec)|Speed-up PyT+TRT/TRT|Avg mels generated (81 mels=1 sec of speech)|Avg audio length (s)|Avg RTF|
 |---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|
-|PyT+TRT|1| 128| FP16| 1.14| 0.02| 1.16| 1.17| 1.20| 136,865| 1.40| 611| 7.09| 6.20|
-|PyT    |1| 128| FP16| 1.58| 0.07| 1.67| 1.70| 1.74| 98,101| 1.00| 605| 7.03| 4.45|
+|PyT+TRT|1| 128| FP16| 1.14| 0.02| 1.16| 1.16| 1.21| 137,050| 1.45| 611| 7.09| 6.20|
+|PyT    |1| 128| FP16| 1.63| 0.07| 1.71| 1.73| 1.81|  94,758| 1.00| 601| 6.98| 4.30|